{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AE72JTNISJ6LLFHXJHFFTFDCIE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6dbe91da23fcc0ff68aca40f9505613b067ede0b18063eb6d0d2b57502167cd8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-05-18T09:47:53Z","title_canon_sha256":"5bd2a7d1d6cbc177c7d77db1aad874b87c04766a25ebdd26ad5b3cc565e3c634"},"schema_version":"1.0","source":{"id":"2605.18141","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18141","created_at":"2026-05-20T00:05:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18141v1","created_at":"2026-05-20T00:05:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18141","created_at":"2026-05-20T00:05:18Z"},{"alias_kind":"pith_short_12","alias_value":"AE72JTNISJ6L","created_at":"2026-05-20T00:05:18Z"},{"alias_kind":"pith_short_16","alias_value":"AE72JTNISJ6LLFHX","created_at":"2026-05-20T00:05:18Z"},{"alias_kind":"pith_short_8","alias_value":"AE72JTNI","created_at":"2026-05-20T00:05:18Z"}],"graph_snapshots":[{"event_id":"sha256:0d17674c4864160bc3ef4a8cfa617172288acccce4e519b751ebacfa1285c29a","target":"graph","created_at":"2026-05-20T00:05:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T23:41:59.108959Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.382558Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.18141/integrity.json","findings":[],"snapshot_sha256":"5bdc4bf723982a07f976422a43f5d99244a2fce0d459e860f0b8fa77e7305339","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-Policy Self-Distillation (OPSD) introduces a unified learning framework in which a single large language model simultaneously serves as both teacher and student. Unlike conventional knowledge distillation that relies on a separate, often larger teacher model, OPSD operates under different contextual roles: the teacher policy is granted privileged access to verified reasoning traces, while the student policy observes only the problem statement. OPSD is trained to minimize per-token distributional divergence between the two roles over trajectories sampled from the student itself, thereby alig","authors_text":"Fangming Cui, Jiahong Li, Sunan Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-05-18T09:47:53Z","title":"A Brief Overview: On-Policy Self-Distillation In Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18141","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:575c44d79c185826cc3bedd58d63fd811c439ceae6218c3895ea5fca5cfbd665","target":"record","created_at":"2026-05-20T00:05:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6dbe91da23fcc0ff68aca40f9505613b067ede0b18063eb6d0d2b57502167cd8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-05-18T09:47:53Z","title_canon_sha256":"5bd2a7d1d6cbc177c7d77db1aad874b87c04766a25ebdd26ad5b3cc565e3c634"},"schema_version":"1.0","source":{"id":"2605.18141","kind":"arxiv","version":1}},"canonical_sha256":"013fa4cda8927cb594f749ca599462411f4d30e4c148d2ebf16bfe3d173a40e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"013fa4cda8927cb594f749ca599462411f4d30e4c148d2ebf16bfe3d173a40e0","first_computed_at":"2026-05-20T00:05:18.428447Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:18.428447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JFYM6351DYUufjkIBkYBuHXCRJ11E2H0FFcIdFUzxqlbAxoDbuZizlRdIPpJa2KrB4as8KM2FTAJGTKcQmldDw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:18.429352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18141","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:575c44d79c185826cc3bedd58d63fd811c439ceae6218c3895ea5fca5cfbd665","sha256:0d17674c4864160bc3ef4a8cfa617172288acccce4e519b751ebacfa1285c29a"],"state_sha256":"31778f3f0e62822735c177e8931623923b984bafb74e79b89e92d011c75d5718"}